Extraction of Non-Binary Blotch Mattes.
KOKARAM, ANIL CHRISTOPHER
Metadata:Show full item record
Citation:Ahmed, Mohamed A.; Pitie, Francois; Kokaram, Anil C., Extraction of Non-Binary Blotch Mattes., Image Processing (ICIP), 2009 16th IEEE International Conference on , IEEE Conference on image Processing (ICIP'09)., Cairo, Egypt, IEEE, 2009, 2757 - 2760
Automated blotch removal is important in film restoration and typically involves a detection/interpolation step. Current algorithms model the corruption as a binary mixture between the original, clean images and an opaque (dirt) field. This typically causes incomplete blotch removal that manifests as blotch haloes in reconstruction. This paper proposes a new approach by modeling the corruption as a continuous mixture between the two components and generating a solution using a Bayesian framework. We use novel priors, propose a computationally efficient scheme for implementation and our results show more complete blotch reconstruction.
Other Titles:Image Processing (ICIP), 2009 16th IEEE International Conference on
IEEE Conference on image Processing (ICIP'09).
Irish Research Council for Science Engineering and Technology
Science Foundation Ireland
Keywords:Blotch, transparency, Bayesian matting, MRF, removal, opacity, non-binary, matte, frames, fusion.